Reqistry MCP server
dev.reqistry/mcpreqistry.devstreamable-httpv2.0.0Scanned
Discover, compare, and monitor 1,400+ APIs directly from your AI coding agent.
16 tools: 5 change things and 11 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Reqistry MCP server can do
The Reqistry MCP server is published by reqistry.dev, a domain the MCP Registry verified. It has 16 tools. It can create or change data (5 tools: check_health, assess_api_production_safety, suggest_alternatives, submit_api and 1 more), but cannot delete data. 11 tools only read.
1 tool reads private data (get_change_feed).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 2.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
16 tools
Changes things 5Claude Code: ask
assess_api_production_safetyAssess whether an API looks production-safe using Reqistry trust score, health, docs, auth, pricing, CORS, and OpenAPI signals.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Assess whether an API looks production-safe using Reqistry trust score, health, docs, auth, pricing, CORS, and OpenAPI signals.
check_healthTrigger (or return cached) a health check for one API.No findings
Why it is in this group
- The description's first verb is "trigger": a word for a change.
Description, as the server wrote it Trigger (or return cached) a health check for one API. Returns CACHED within cooldown, or QUEUED with a poll URL. Rate-limited per device.
submit_apiSubmit a new API for review.No findings
Why it is in this group
- The name "submit_api" says "submit": a word for a change.
Description, as the server wrote it Submit a new API for review. Creates a 'pending' submission (not immediately published). At least name or link required. Email optional.
suggest_alternativesSuggest healthier alternatives to a weak or dead API.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Suggest healthier alternatives to a weak or dead API. Uses the same category/type matching as Reqistry alternatives.
swap_apiReplace a dead API in-session: status + change-feed evidence for the given slug, alive alternatives with matching facets, and a starter snippet for the top pick.No findings
Why it is in this group
- The description's first verb is "replace": a word for a change.
Description, as the server wrote it Replace a dead API in-session: status + change-feed evidence for the given slug, alive alternatives with matching facets, and a starter snippet for the top pick.
Only reads 11Show 11 read-only tools
compare_apisCompare 2 to 8 APIs side-by-side by id or slug.No findings
Why it is in this group
- The name "compare_apis" says "compare": a word for reading.
Description, as the server wrote it Compare 2 to 8 APIs side-by-side by id or slug. Returns auth, pricing, rate limits, SDKs, response time, CORS, verification, OpenAPI, and trust scores.
get_alternativesFind alternative APIs similar to a given API id — prefers same category, falls back to same API type.No findings
Why it is in this group
- The name "get_alternatives" says "get": a word for reading.
Description, as the server wrote it Find alternative APIs similar to a given API id — prefers same category, falls back to same API type. limit must be 2 or 3 (default 3).
get_apiGet full detail for one API by slug or id, including health, metadata, verification, and warnings.No findings
Why it is in this group
- The name "get_api" says "get": a word for reading.
Description, as the server wrote it Get full detail for one API by slug or id, including health, metadata, verification, and warnings. Use after browsing a category to drill in.
get_api_trust_scoreGet the Reqistry trust score for one API by id or slug.No findings
Why it is in this group
- The name "get_api_trust_score" says "get": a word for reading.
Description, as the server wrote it Get the Reqistry trust score for one API by id or slug. Score covers uptime, response time, docs quality, auth clarity, CORS, pricing clarity, freshness, and OpenAPI availability.
get_category_apisList published APIs in a category by slug (e.g.No findings
Why it is in this group
- The name "get_category_apis" says "get": a word for reading.
Description, as the server wrote it List published APIs in a category by slug (e.g. 'weather', 'finance'). Paginated. Use list_categories first to get a category slug.
get_change_feedRead recent Reqistry API change events: pricing changes, docs moves, OpenAPI changes, health degradation/recovery, and trust-score changes.Reads private dataNo findings
Why it is in this group
- The name "get_change_feed" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "doc": it reads documents.
Description, as the server wrote it Read recent Reqistry API change events: pricing changes, docs moves, OpenAPI changes, health degradation/recovery, and trust-score changes.
get_snippetStarter integration snippet for one catalog API in curl, python, javascript, or typescript.No findings
Why it is in this group
- The name "get_snippet" says "get": a word for reading.
Description, as the server wrote it Starter integration snippet for one catalog API in curl, python, javascript, or typescript. Uses the cataloged base URL verbatim; auth handling reflects the cataloged auth type.
get_use_case_collectionsGet curated use-case packs such as finance dashboards, free AI APIs, travel apps, and no-auth prototype APIs.No findings
Why it is in this group
- The name "get_use_case_collections" says "get": a word for reading.
Description, as the server wrote it Get curated use-case packs such as finance dashboards, free AI APIs, travel apps, and no-auth prototype APIs.
list_categoriesList all active API categories with the number of published APIs in each.No findings
Why it is in this group
- The name "list_categories" says "list": a word for reading.
Description, as the server wrote it List all active API categories with the number of published APIs in each. Use to populate a category filter or browse by topic.
recommend_apisGet recommended APIs — personalized when the device has bookmarks, otherwise random picks.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get recommended APIs — personalized when the device has bookmarks, otherwise random picks. Optional limit (max 50).
search_apisSearch the catalog full-text with facets: q, category (from list_categories), auth (None, API key, OAuth), pricing (free, freemium, paid), alive, limit (1-50).No findings
Why it is in this group
- The name "search_apis" says "search": a word for reading.
Description, as the server wrote it Search the catalog full-text with facets: q, category (from list_categories), auth (None, API key, OAuth), pricing (free, freemium, paid), alive, limit (1-50).
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:52 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.reqistry.dev/mcp: tools/list returned 16 tools to an anonymous client, including check_health (write), assess_api_production_safety (write), suggest_alternatives (write), submit_api (write), swap_api (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:submit_apiChanges thingsinputSchema
Install
Pinned to version 2.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http reqistry https://mcp.reqistry.dev/mcpclaude mcp add --transport http reqistry https://mcp.reqistry.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__reqistry__list_categories",
"mcp__reqistry__get_category_apis",
"mcp__reqistry__get_api",
"mcp__reqistry__get_alternatives",
"mcp__reqistry__get_api_trust_score",
"mcp__reqistry__compare_apis",
"mcp__reqistry__get_change_feed",
"mcp__reqistry__get_use_case_collections",
"mcp__reqistry__recommend_apis",
"mcp__reqistry__search_apis",
"mcp__reqistry__get_snippet"
],
"ask": [
"mcp__reqistry__check_health",
"mcp__reqistry__assess_api_production_safety",
"mcp__reqistry__suggest_alternatives",
"mcp__reqistry__submit_api",
"mcp__reqistry__swap_api"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as reqistry. Review it before you use it.
Capability tags behind 1 rule
- mcp__reqistry__get_change_feed private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/dev.reqistry/mcp/verify?hash=009d8e3965032b608640c1bff1fb6362fc658a68de86a90b7a00c3a4b95c9985" | jq -e '.changed == false'Pinned hash 009d8e396503, from Nov 15, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/dev.reqistry/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/dev.reqistry/mcp)Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.
Reqistry MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Reqistry MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Reqistry MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Reqistry MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Reqistry MCP server have?
- 16 tools: 5 write, 11 read. check_health, assess_api_production_safety, suggest_alternatives, submit_api, swap_api, list_categories, get_category_apis, get_api and 8 more.
Does the Reqistry MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Reqistry MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Reqistry MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 2, 2026. Every change is on this page and in its Atom feed.